Triple

T6148353
Position Surface form Disambiguated ID Type / Status
Subject Kiranti languages E137135 entity
Predicate hasMember P10 FINISHED
Object Puma language
Puma language is a Kiranti language of the Sino-Tibetan family spoken by the Puma people of eastern Nepal.
 E572266 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Puma language | Statement: [Kiranti languages, hasMember, Puma language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Puma language
Context triple: [Kiranti languages, hasMember, Puma language]
  • A. Pumi language
    The Pumi language is a Sino-Tibetan language spoken primarily by the Pumi ethnic group in southwestern China, notable for its complex phonology and endangered status.
  • B. Mono language
    Mono language is a Native American Uto-Aztecan language traditionally spoken by the Mono people of eastern California.
  • C. Pokomo language
    The Pokomo language is a Bantu language spoken primarily by the Pokomo people along Kenya’s Tana River.
  • D. Uma language
    Uma is an Austronesian language of the Celebic subgroup spoken primarily in Central Sulawesi, Indonesia.
  • E. Puyuma language
    The Puyuma language is an endangered Austronesian language spoken by the Puyuma Indigenous people of southeastern Taiwan.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Puma language
Triple: [Kiranti languages, hasMember, Puma language]
Generated description
Puma language is a Kiranti language of the Sino-Tibetan family spoken by the Puma people of eastern Nepal.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Puma language
Target entity description: Puma language is a Kiranti language of the Sino-Tibetan family spoken by the Puma people of eastern Nepal.
  • A. Pumi language
    The Pumi language is a Sino-Tibetan language spoken primarily by the Pumi ethnic group in southwestern China, notable for its complex phonology and endangered status.
  • B. Mono language
    Mono language is a Native American Uto-Aztecan language traditionally spoken by the Mono people of eastern California.
  • C. Pokomo language
    The Pokomo language is a Bantu language spoken primarily by the Pokomo people along Kenya’s Tana River.
  • D. Uma language
    Uma is an Austronesian language of the Celebic subgroup spoken primarily in Central Sulawesi, Indonesia.
  • E. Puyuma language
    The Puyuma language is an endangered Austronesian language spoken by the Puyuma Indigenous people of southeastern Taiwan.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69c008a2c6308190a56519b22d55d083 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c05ce07fb081909278088e9e2e2959 completed March 22, 2026, 9:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69c13603730881909b3991c7262509b5 completed March 23, 2026, 12:45 p.m.
NEDg Description generation batch_69c139f6f11c81909eb0b2ab809de079 completed March 23, 2026, 1:02 p.m.
NED2 Entity disambiguation (via description) batch_69c13a5f53ec8190be24f37fc5fb7f32 completed March 23, 2026, 1:04 p.m.
Created at: March 22, 2026, 4:16 p.m.